Instructions to use OmAhire369/safe-genai-ppo-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OmAhire369/safe-genai-ppo-full with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="OmAhire369/safe-genai-ppo-full")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OmAhire369/safe-genai-ppo-full")
model = AutoModelForCausalLM.from_pretrained("OmAhire369/safe-genai-ppo-full", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OmAhire369/safe-genai-ppo-full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OmAhire369/safe-genai-ppo-full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OmAhire369/safe-genai-ppo-full",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OmAhire369/safe-genai-ppo-full

SGLang

How to use OmAhire369/safe-genai-ppo-full with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "OmAhire369/safe-genai-ppo-full" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OmAhire369/safe-genai-ppo-full",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "OmAhire369/safe-genai-ppo-full" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OmAhire369/safe-genai-ppo-full",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OmAhire369/safe-genai-ppo-full with Docker Model Runner:
```
docker model run hf.co/OmAhire369/safe-genai-ppo-full
```

safe-genai-ppo-full / value_head.pt

OmAhire369

ppo / full checkpoint

ecd48aa verified about 1 month ago

History Blame Contribute Delete

6.08 kB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 2af2907d00f90215e79f9e070b15b3b1c47c4c524e8f5a860a7667acb3b54ccd
Size of remote file:: 6.08 kB
SHA256:: 41fcd877ea209cc3eeb14e5001cc45e57be0d4559b87b94b2107aff25d06e12b

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.